© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16740
    Prev
    Next
    INDEX
    Explanations

    ancient history and dynasties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±±èĮ¶
    -0.09
     Hudson
    -0.08
    rof
    -0.07
     Mastercard
    -0.07
     Cong
    -0.07
     MasterCard
    -0.07
     congen
    -0.07
     Ivory
    -0.07
    림
    -0.07
    èĺij
    -0.07
    POSITIVE LOGITS
    西æ±ī
    0.13
    秦å§ĭçļĩ
    0.12
    æ±īæѦå¸Ŀ
    0.11
    æ±ī代
    0.11
    秦çİĭ
    0.10
    åħ¬åħĥåīį
    0.10
    å§ĭçļĩ
    0.10
    åĪĺéĤ¦
    0.10
    åħµé©¬ä¿ij
    0.09
    项羽
    0.09
    Activations Density 0.025%

    No Known Activations